Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Abstract: Gestational age (GA) is unknown in half of all births in low- and middle- income countries. The gold standard is to measure the fetal crown rump length at 11-14 weeks, but in these settings most women present much later in pregnancy. Assessing GA in the second and third trimesters is undertaken using fetal size, but the accuracy of this approach is poor due to variation in fetal size, in particular fetal growth restriction. Machine learning is expanding rapidly and has been shown to have great potential in other areas of medicine and obstetrics. I will present my work on using machine learning to estimate GA based on ultrasound images acquired in the second and third trimesters. The algorithm estimates GA based on appearance of the ultrasound, without any information on fetal size or scale. This method outperforms current biometry-based methods with a mean absolute error of 3 and 4 days in the second and third trimesters respectively. I have also shown that it performs well in small and large for GA babies. Advances in machine learning within obstetric care have outpaced research into explainability, acceptability, ethics and trust. In order to examine the opinions of key stakeholders using qualitative approaches, I will also present my work from a multicentre, international study in Nigeria, Rwanda, Canada and the UK. This involved semi-structured interviews with maternity healthcare workers and pregnant women.